aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/xen/events.c
blob: 4b33acd8ed4ef262bfa43940eab2be7a3deb66f5 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
/*
 * Xen event channels
 *
 * Xen models interrupts with abstract event channels.  Because each
 * domain gets 1024 event channels, but NR_IRQ is not that large, we
 * must dynamically map irqs<->event channels.  The event channels
 * interface with the rest of the kernel by defining a xen interrupt
 * chip.  When an event is received, it is mapped to an irq and sent
 * through the normal interrupt processing path.
 *
 * There are four kinds of events which can be mapped to an event
 * channel:
 *
 * 1. Inter-domain notifications.  This includes all the virtual
 *    device events, since they're driven by front-ends in another domain
 *    (typically dom0).
 * 2. VIRQs, typically used for timers.  These are per-cpu events.
 * 3. IPIs.
 * 4. PIRQs - Hardware interrupts.
 *
 * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
 */

#include <linux/linkage.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/module.h>
#include <linux/string.h>
#include <linux/bootmem.h>
#include <linux/slab.h>
#include <linux/irqnr.h>
#include <linux/pci.h>

#include <asm/desc.h>
#include <asm/ptrace.h>
#include <asm/irq.h>
#include <asm/idle.h>
#include <asm/io_apic.h>
#include <asm/sync_bitops.h>
#include <asm/xen/page.h>
#include <asm/xen/pci.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>

#include <xen/xen.h>
#include <xen/hvm.h>
#include <xen/xen-ops.h>
#include <xen/events.h>
#include <xen/interface/xen.h>
#include <xen/interface/event_channel.h>
#include <xen/interface/hvm/hvm_op.h>
#include <xen/interface/hvm/params.h>

/*
 * This lock protects updates to the following mapping and reference-count
 * arrays. The lock does not need to be acquired to read the mapping tables.
 */
static DEFINE_MUTEX(irq_mapping_update_lock);

static LIST_HEAD(xen_irq_list_head);

/* IRQ <-> VIRQ mapping. */
static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};

/* IRQ <-> IPI mapping */
static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};

/* Interrupt types. */
enum xen_irq_type {
	IRQT_UNBOUND = 0,
	IRQT_PIRQ,
	IRQT_VIRQ,
	IRQT_IPI,
	IRQT_EVTCHN
};

/*
 * Packed IRQ information:
 * type - enum xen_irq_type
 * event channel - irq->event channel mapping
 * cpu - cpu this event channel is bound to
 * index - type-specific information:
 *    PIRQ - vector, with MSB being "needs EIO", or physical IRQ of the HVM
 *           guest, or GSI (real passthrough IRQ) of the device.
 *    VIRQ - virq number
 *    IPI - IPI vector
 *    EVTCHN -
 */
struct irq_info {
	struct list_head list;
	int refcnt;
	enum xen_irq_type type;	/* type */
	unsigned irq;
	unsigned short evtchn;	/* event channel */
	unsigned short cpu;	/* cpu bound */

	union {
		unsigned short virq;
		enum ipi_vector ipi;
		struct {
			unsigned short pirq;
			unsigned short gsi;
			unsigned char vector;
			unsigned char flags;
			uint16_t domid;
		} pirq;
	} u;
};
#define PIRQ_NEEDS_EOI	(1 << 0)
#define PIRQ_SHAREABLE	(1 << 1)

static int *evtchn_to_irq;
static unsigned long *pirq_eoi_map;
static bool (*pirq_needs_eoi)(unsigned irq);

static DEFINE_PER_CPU(unsigned long [NR_EVENT_CHANNELS/BITS_PER_LONG],
		      cpu_evtchn_mask);

/* Xen will never allocate port zero for any purpose. */
#define VALID_EVTCHN(chn)	((chn) != 0)

static struct irq_chip xen_dynamic_chip;
static struct irq_chip xen_percpu_chip;
static struct irq_chip xen_pirq_chip;
static void enable_dynirq(struct irq_data *data);
static void disable_dynirq(struct irq_data *data);

/* Get info for IRQ */
static struct irq_info *info_for_irq(unsigned irq)
{
	return irq_get_handler_data(irq);
}

/* Constructors for packed IRQ information. */
static void xen_irq_info_common_init(struct irq_info *info,
				     unsigned irq,
				     enum xen_irq_type type,
				     unsigned short evtchn,
				     unsigned short cpu)
{

	BUG_ON(info->type != IRQT_UNBOUND && info->type != type);

	info->type = type;
	info->irq = irq;
	info->evtchn = evtchn;
	info->cpu = cpu;

	evtchn_to_irq[evtchn] = irq;
}

static void xen_irq_info_evtchn_init(unsigned irq,
				     unsigned short evtchn)
{
	struct irq_info *info = info_for_irq(irq);

	xen_irq_info_common_init(info, irq, IRQT_EVTCHN, evtchn, 0);
}

static void xen_irq_info_ipi_init(unsigned cpu,
				  unsigned irq,
				  unsigned short evtchn,
				  enum ipi_vector ipi)
{
	struct irq_info *info = info_for_irq(irq);

	xen_irq_info_common_init(info, irq, IRQT_IPI, evtchn, 0);

	info->u.ipi = ipi;

	per_cpu(ipi_to_irq, cpu)[ipi] = irq;
}

static void xen_irq_info_virq_init(unsigned cpu,
				   unsigned irq,
				   unsigned short evtchn,
				   unsigned short virq)
{
	struct irq_info *info = info_for_irq(irq);

	xen_irq_info_common_init(info, irq, IRQT_VIRQ, evtchn, 0);

	info->u.virq = virq;

	per_cpu(virq_to_irq, cpu)[virq] = irq;
}

static void xen_irq_info_pirq_init(unsigned irq,
				   unsigned short evtchn,
				   unsigned short pirq,
				   unsigned short gsi,
				   unsigned short vector,
				   uint16_t domid,
				   unsigned char flags)
{
	struct irq_info *info = info_for_irq(irq);

	xen_irq_info_common_init(info, irq, IRQT_PIRQ, evtchn, 0);

	info->u.pirq.pirq = pirq;
	info->u.pirq.gsi = gsi;
	info->u.pirq.vector = vector;
	info->u.pirq.domid = domid;
	info->u.pirq.flags = flags;
}

/*
 * Accessors for packed IRQ information.
 */
static unsigned int evtchn_from_irq(unsigned irq)
{
	if (unlikely(WARN(irq < 0 || irq >= nr_irqs, "Invalid irq %d!\n", irq)))
		return 0;

	return info_for_irq(irq)->evtchn;
}

unsigned irq_from_evtchn(unsigned int evtchn)
{
	return evtchn_to_irq[evtchn];
}
EXPORT_SYMBOL_GPL(irq_from_evtchn);

static enum ipi_vector ipi_from_irq(unsigned irq)
{
	struct irq_info *info = info_for_irq(irq);

	BUG_ON(info == NULL);
	BUG_ON(info->type != IRQT_IPI);

	return info->u.ipi;
}

static unsigned virq_from_irq(unsigned irq)
{
	struct irq_info *info = info_for_irq(irq);

	BUG_ON(info == NULL);
	BUG_ON(info->type != IRQT_VIRQ);

	return info->u.virq;
}

static unsigned pirq_from_irq(unsigned irq)
{
	struct irq_info *info = info_for_irq(irq);

	BUG_ON(info == NULL);
	BUG_ON(info->type != IRQT_PIRQ);

	return info->u.pirq.pirq;
}

static enum xen_irq_type type_from_irq(unsigned irq)
{
	return info_for_irq(irq)->type;
}

static unsigned cpu_from_irq(unsigned irq)
{
	return info_for_irq(irq)->cpu;
}

static unsigned int cpu_from_evtchn(unsigned int evtchn)
{
	int irq = evtchn_to_irq[evtchn];
	unsigned ret = 0;

	if (irq != -1)
		ret = cpu_from_irq(irq);

	return ret;
}

static bool pirq_check_eoi_map(unsigned irq)
{
	return test_bit(irq, pirq_eoi_map);
}

static bool pirq_needs_eoi_flag(unsigned irq)
{
	struct irq_info *info = info_for_irq(irq);
	BUG_ON(info->type != IRQT_PIRQ);

	return info->u.pirq.flags & PIRQ_NEEDS_EOI;
}

static inline unsigned long active_evtchns(unsigned int cpu,
					   struct shared_info *sh,
					   unsigned int idx)
{
	return sh->evtchn_pending[idx] &
		per_cpu(cpu_evtchn_mask, cpu)[idx] &
		~sh->evtchn_mask[idx];
}

static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
{
	int irq = evtchn_to_irq[chn];

	BUG_ON(irq == -1);
#ifdef CONFIG_SMP
	cpumask_copy(irq_to_desc(irq)->irq_data.affinity, cpumask_of(cpu));
#endif

	clear_bit(chn, per_cpu(cpu_evtchn_mask, cpu_from_irq(irq)));
	set_bit(chn, per_cpu(cpu_evtchn_mask, cpu));

	info_for_irq(irq)->cpu = cpu;
}

static void init_evtchn_cpu_bindings(void)
{
	int i;
#ifdef CONFIG_SMP
	struct irq_info *info;

	/* By default all event channels notify CPU#0. */
	list_for_each_entry(info, &xen_irq_list_head, list) {
		struct irq_desc *desc = irq_to_desc(info->irq);
		cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
	}
#endif

	for_each_possible_cpu(i)
		memset(per_cpu(cpu_evtchn_mask, i),
		       (i == 0) ? ~0 : 0, sizeof(*per_cpu(cpu_evtchn_mask, i)));
}

static inline void clear_evtchn(int port)
{
	struct shared_info *s = HYPERVISOR_shared_info;
	sync_clear_bit(port, &s->evtchn_pending[0]);
}

static inline void set_evtchn(int port)
{
	struct shared_info *s = HYPERVISOR_shared_info;
	sync_set_bit(port, &s->evtchn_pending[0]);
}

static inline int test_evtchn(int port)
{
	struct shared_info *s = HYPERVISOR_shared_info;
	return sync_test_bit(port, &s->evtchn_pending[0]);
}


/**
 * notify_remote_via_irq - send event to remote end of event channel via irq
 * @irq: irq of event channel to send event to
 *
 * Unlike notify_remote_via_evtchn(), this is safe to use across
 * save/restore. Notifications on a broken connection are silently
 * dropped.
 */
void notify_remote_via_irq(int irq)
{
	int evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn))
		notify_remote_via_evtchn(evtchn);
}
EXPORT_SYMBOL_GPL(notify_remote_via_irq);

static void mask_evtchn(int port)
{
	struct shared_info *s = HYPERVISOR_shared_info;
	sync_set_bit(port, &s->evtchn_mask[0]);
}

static void unmask_evtchn(int port)
{
	struct shared_info *s = HYPERVISOR_shared_info;
	unsigned int cpu = get_cpu();

	BUG_ON(!irqs_disabled());

	/* Slow path (hypercall) if this is a non-local port. */
	if (unlikely(cpu != cpu_from_evtchn(port))) {
		struct evtchn_unmask unmask = { .port = port };
		(void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
	} else {
		struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu);

		sync_clear_bit(port, &s->evtchn_mask[0]);

		/*
		 * The following is basically the equivalent of
		 * 'hw_resend_irq'. Just like a real IO-APIC we 'lose
		 * the interrupt edge' if the channel is masked.
		 */
		if (sync_test_bit(port, &s->evtchn_pending[0]) &&
		    !sync_test_and_set_bit(port / BITS_PER_LONG,
					   &vcpu_info->evtchn_pending_sel))
			vcpu_info->evtchn_upcall_pending = 1;
	}

	put_cpu();
}

static void xen_irq_init(unsigned irq)
{
	struct irq_info *info;
#ifdef CONFIG_SMP
	struct irq_desc *desc = irq_to_desc(irq);

	/* By default all event channels notify CPU#0. */
	cpumask_copy(desc->irq_data.affinity, cpumask_of(0));
#endif

	info = kzalloc(sizeof(*info), GFP_KERNEL);
	if (info == NULL)
		panic("Unable to allocate metadata for IRQ%d\n", irq);

	info->type = IRQT_UNBOUND;
	info->refcnt = -1;

	irq_set_handler_data(irq, info);

	list_add_tail(&info->list, &xen_irq_list_head);
}

static int __must_check xen_allocate_irq_dynamic(void)
{
	int first = 0;
	int irq;

#ifdef CONFIG_X86_IO_APIC
	/*
	 * For an HVM guest or domain 0 which see "real" (emulated or
	 * actual respectively) GSIs we allocate dynamic IRQs
	 * e.g. those corresponding to event channels or MSIs
	 * etc. from the range above those "real" GSIs to avoid
	 * collisions.
	 */
	if (xen_initial_domain() || xen_hvm_domain())
		first = get_nr_irqs_gsi();
#endif

	irq = irq_alloc_desc_from(first, -1);

	if (irq >= 0)
		xen_irq_init(irq);

	return irq;
}

static int __must_check xen_allocate_irq_gsi(unsigned gsi)
{
	int irq;

	/*
	 * A PV guest has no concept of a GSI (since it has no ACPI
	 * nor access to/knowledge of the physical APICs). Therefore
	 * all IRQs are dynamically allocated from the entire IRQ
	 * space.
	 */
	if (xen_pv_domain() && !xen_initial_domain())
		return xen_allocate_irq_dynamic();

	/* Legacy IRQ descriptors are already allocated by the arch. */
	if (gsi < NR_IRQS_LEGACY)
		irq = gsi;
	else
		irq = irq_alloc_desc_at(gsi, -1);

	xen_irq_init(irq);

	return irq;
}

static void xen_free_irq(unsigned irq)
{
	struct irq_info *info = irq_get_handler_data(irq);

	list_del(&info->list);

	irq_set_handler_data(irq, NULL);

	WARN_ON(info->refcnt > 0);

	kfree(info);

	/* Legacy IRQ descriptors are managed by the arch. */
	if (irq < NR_IRQS_LEGACY)
		return;

	irq_free_desc(irq);
}

static void pirq_query_unmask(int irq)
{
	struct physdev_irq_status_query irq_status;
	struct irq_info *info = info_for_irq(irq);

	BUG_ON(info->type != IRQT_PIRQ);

	irq_status.irq = pirq_from_irq(irq);
	if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
		irq_status.flags = 0;

	info->u.pirq.flags &= ~PIRQ_NEEDS_EOI;
	if (irq_status.flags & XENIRQSTAT_needs_eoi)
		info->u.pirq.flags |= PIRQ_NEEDS_EOI;
}

static bool probing_irq(int irq)
{
	struct irq_desc *desc = irq_to_desc(irq);

	return desc && desc->action == NULL;
}

static void eoi_pirq(struct irq_data *data)
{
	int evtchn = evtchn_from_irq(data->irq);
	struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
	int rc = 0;

	irq_move_irq(data);

	if (VALID_EVTCHN(evtchn))
		clear_evtchn(evtchn);

	if (pirq_needs_eoi(data->irq)) {
		rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
		WARN_ON(rc);
	}
}

static void mask_ack_pirq(struct irq_data *data)
{
	disable_dynirq(data);
	eoi_pirq(data);
}

static unsigned int __startup_pirq(unsigned int irq)
{
	struct evtchn_bind_pirq bind_pirq;
	struct irq_info *info = info_for_irq(irq);
	int evtchn = evtchn_from_irq(irq);
	int rc;

	BUG_ON(info->type != IRQT_PIRQ);

	if (VALID_EVTCHN(evtchn))
		goto out;

	bind_pirq.pirq = pirq_from_irq(irq);
	/* NB. We are happy to share unless we are probing. */
	bind_pirq.flags = info->u.pirq.flags & PIRQ_SHAREABLE ?
					BIND_PIRQ__WILL_SHARE : 0;
	rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_pirq, &bind_pirq);
	if (rc != 0) {
		if (!probing_irq(irq))
			printk(KERN_INFO "Failed to obtain physical IRQ %d\n",
			       irq);
		return 0;
	}
	evtchn = bind_pirq.port;

	pirq_query_unmask(irq);

	evtchn_to_irq[evtchn] = irq;
	bind_evtchn_to_cpu(evtchn, 0);
	info->evtchn = evtchn;

out:
	unmask_evtchn(evtchn);
	eoi_pirq(irq_get_irq_data(irq));

	return 0;
}

static unsigned int startup_pirq(struct irq_data *data)
{
	return __startup_pirq(data->irq);
}

static void shutdown_pirq(struct irq_data *data)
{
	struct evtchn_close close;
	unsigned int irq = data->irq;
	struct irq_info *info = info_for_irq(irq);
	int evtchn = evtchn_from_irq(irq);

	BUG_ON(info->type != IRQT_PIRQ);

	if (!VALID_EVTCHN(evtchn))
		return;

	mask_evtchn(evtchn);

	close.port = evtchn;
	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
		BUG();

	bind_evtchn_to_cpu(evtchn, 0);
	evtchn_to_irq[evtchn] = -1;
	info->evtchn = 0;
}

static void enable_pirq(struct irq_data *data)
{
	startup_pirq(data);
}

static void disable_pirq(struct irq_data *data)
{
	disable_dynirq(data);
}

static int find_irq_by_gsi(unsigned gsi)
{
	struct irq_info *info;

	list_for_each_entry(info, &xen_irq_list_head, list) {
		if (info->type != IRQT_PIRQ)
			continue;

		if (info->u.pirq.gsi == gsi)
			return info->irq;
	}

	return -1;
}

/*
 * Do not make any assumptions regarding the relationship between the
 * IRQ number returned here and the Xen pirq argument.
 *
 * Note: We don't assign an event channel until the irq actually started
 * up.  Return an existing irq if we've already got one for the gsi.
 *
 * Shareable implies level triggered, not shareable implies edge
 * triggered here.
 */
int xen_bind_pirq_gsi_to_irq(unsigned gsi,
			     unsigned pirq, int shareable, char *name)
{
	int irq = -1;
	struct physdev_irq irq_op;

	mutex_lock(&irq_mapping_update_lock);

	irq = find_irq_by_gsi(gsi);
	if (irq != -1) {
		printk(KERN_INFO "xen_map_pirq_gsi: returning irq %d for gsi %u\n",
		       irq, gsi);
		goto out;
	}

	irq = xen_allocate_irq_gsi(gsi);
	if (irq < 0)
		goto out;

	irq_op.irq = irq;
	irq_op.vector = 0;

	/* Only the privileged domain can do this. For non-priv, the pcifront
	 * driver provides a PCI bus that does the call to do exactly
	 * this in the priv domain. */
	if (xen_initial_domain() &&
	    HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) {
		xen_free_irq(irq);
		irq = -ENOSPC;
		goto out;
	}

	xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector, DOMID_SELF,
			       shareable ? PIRQ_SHAREABLE : 0);

	pirq_query_unmask(irq);
	/* We try to use the handler with the appropriate semantic for the
	 * type of interrupt: if the interrupt is an edge triggered
	 * interrupt we use handle_edge_irq.
	 *
	 * On the other hand if the interrupt is level triggered we use
	 * handle_fasteoi_irq like the native code does for this kind of
	 * interrupts.
	 *
	 * Depending on the Xen version, pirq_needs_eoi might return true
	 * not only for level triggered interrupts but for edge triggered
	 * interrupts too. In any case Xen always honors the eoi mechanism,
	 * not injecting any more pirqs of the same kind if the first one
	 * hasn't received an eoi yet. Therefore using the fasteoi handler
	 * is the right choice either way.
	 */
	if (shareable)
		irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
				handle_fasteoi_irq, name);
	else
		irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
				handle_edge_irq, name);

out:
	mutex_unlock(&irq_mapping_update_lock);

	return irq;
}

#ifdef CONFIG_PCI_MSI
int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc)
{
	int rc;
	struct physdev_get_free_pirq op_get_free_pirq;

	op_get_free_pirq.type = MAP_PIRQ_TYPE_MSI;
	rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq);

	WARN_ONCE(rc == -ENOSYS,
		  "hypervisor does not support the PHYSDEVOP_get_free_pirq interface\n");

	return rc ? -1 : op_get_free_pirq.pirq;
}

int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
			     int pirq, int vector, const char *name,
			     domid_t domid)
{
	int irq, ret;

	mutex_lock(&irq_mapping_update_lock);

	irq = xen_allocate_irq_dynamic();
	if (irq < 0)
		goto out;

	irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq,
			name);

	xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, domid, 0);
	ret = irq_set_msi_desc(irq, msidesc);
	if (ret < 0)
		goto error_irq;
out:
	mutex_unlock(&irq_mapping_update_lock);
	return irq;
error_irq:
	mutex_unlock(&irq_mapping_update_lock);
	xen_free_irq(irq);
	return ret;
}
#endif

int xen_destroy_irq(int irq)
{
	struct irq_desc *desc;
	struct physdev_unmap_pirq unmap_irq;
	struct irq_info *info = info_for_irq(irq);
	int rc = -ENOENT;

	mutex_lock(&irq_mapping_update_lock);

	desc = irq_to_desc(irq);
	if (!desc)
		goto out;

	if (xen_initial_domain()) {
		unmap_irq.pirq = info->u.pirq.pirq;
		unmap_irq.domid = info->u.pirq.domid;
		rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq);
		/* If another domain quits without making the pci_disable_msix
		 * call, the Xen hypervisor takes care of freeing the PIRQs
		 * (free_domain_pirqs).
		 */
		if ((rc == -ESRCH && info->u.pirq.domid != DOMID_SELF))
			printk(KERN_INFO "domain %d does not have %d anymore\n",
				info->u.pirq.domid, info->u.pirq.pirq);
		else if (rc) {
			printk(KERN_WARNING "unmap irq failed %d\n", rc);
			goto out;
		}
	}

	xen_free_irq(irq);

out:
	mutex_unlock(&irq_mapping_update_lock);
	return rc;
}

int xen_irq_from_pirq(unsigned pirq)
{
	int irq;

	struct irq_info *info;

	mutex_lock(&irq_mapping_update_lock);

	list_for_each_entry(info, &xen_irq_list_head, list) {
		if (info->type != IRQT_PIRQ)
			continue;
		irq = info->irq;
		if (info->u.pirq.pirq == pirq)
			goto out;
	}
	irq = -1;
out:
	mutex_unlock(&irq_mapping_update_lock);

	return irq;
}


int xen_pirq_from_irq(unsigned irq)
{
	return pirq_from_irq(irq);
}
EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
int bind_evtchn_to_irq(unsigned int evtchn)
{
	int irq;

	mutex_lock(&irq_mapping_update_lock);

	irq = evtchn_to_irq[evtchn];

	if (irq == -1) {
		irq = xen_allocate_irq_dynamic();
		if (irq == -1)
			goto out;

		irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
					      handle_edge_irq, "event");

		xen_irq_info_evtchn_init(irq, evtchn);
	}

out:
	mutex_unlock(&irq_mapping_update_lock);

	return irq;
}
EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);

static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
{
	struct evtchn_bind_ipi bind_ipi;
	int evtchn, irq;

	mutex_lock(&irq_mapping_update_lock);

	irq = per_cpu(ipi_to_irq, cpu)[ipi];

	if (irq == -1) {
		irq = xen_allocate_irq_dynamic();
		if (irq < 0)
			goto out;

		irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
					      handle_percpu_irq, "ipi");

		bind_ipi.vcpu = cpu;
		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
						&bind_ipi) != 0)
			BUG();
		evtchn = bind_ipi.port;

		xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);

		bind_evtchn_to_cpu(evtchn, cpu);
	}

 out:
	mutex_unlock(&irq_mapping_update_lock);
	return irq;
}

static int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
					  unsigned int remote_port)
{
	struct evtchn_bind_interdomain bind_interdomain;
	int err;

	bind_interdomain.remote_dom  = remote_domain;
	bind_interdomain.remote_port = remote_port;

	err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
					  &bind_interdomain);

	return err ? : bind_evtchn_to_irq(bind_interdomain.local_port);
}

static int find_virq(unsigned int virq, unsigned int cpu)
{
	struct evtchn_status status;
	int port, rc = -ENOENT;

	memset(&status, 0, sizeof(status));
	for (port = 0; port <= NR_EVENT_CHANNELS; port++) {
		status.dom = DOMID_SELF;
		status.port = port;
		rc = HYPERVISOR_event_channel_op(EVTCHNOP_status, &status);
		if (rc < 0)
			continue;
		if (status.status != EVTCHNSTAT_virq)
			continue;
		if (status.u.virq == virq && status.vcpu == cpu) {
			rc = port;
			break;
		}
	}
	return rc;
}

int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
{
	struct evtchn_bind_virq bind_virq;
	int evtchn, irq, ret;

	mutex_lock(&irq_mapping_update_lock);

	irq = per_cpu(virq_to_irq, cpu)[virq];

	if (irq == -1) {
		irq = xen_allocate_irq_dynamic();
		if (irq == -1)
			goto out;

		irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
					      handle_percpu_irq, "virq");

		bind_virq.virq = virq;
		bind_virq.vcpu = cpu;
		ret = HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
						&bind_virq);
		if (ret == 0)
			evtchn = bind_virq.port;
		else {
			if (ret == -EEXIST)
				ret = find_virq(virq, cpu);
			BUG_ON(ret < 0);
			evtchn = ret;
		}

		xen_irq_info_virq_init(cpu, irq, evtchn, virq);

		bind_evtchn_to_cpu(evtchn, cpu);
	}

out:
	mutex_unlock(&irq_mapping_update_lock);

	return irq;
}

static void unbind_from_irq(unsigned int irq)
{
	struct evtchn_close close;
	int evtchn = evtchn_from_irq(irq);
	struct irq_info *info = irq_get_handler_data(irq);

	mutex_lock(&irq_mapping_update_lock);

	if (info->refcnt > 0) {
		info->refcnt--;
		if (info->refcnt != 0)
			goto done;
	}

	if (VALID_EVTCHN(evtchn)) {
		close.port = evtchn;
		if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
			BUG();

		switch (type_from_irq(irq)) {
		case IRQT_VIRQ:
			per_cpu(virq_to_irq, cpu_from_evtchn(evtchn))
				[virq_from_irq(irq)] = -1;
			break;
		case IRQT_IPI:
			per_cpu(ipi_to_irq, cpu_from_evtchn(evtchn))
				[ipi_from_irq(irq)] = -1;
			break;
		default:
			break;
		}

		/* Closed ports are implicitly re-bound to VCPU0. */
		bind_evtchn_to_cpu(evtchn, 0);

		evtchn_to_irq[evtchn] = -1;
	}

	BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND);

	xen_free_irq(irq);

 done:
	mutex_unlock(&irq_mapping_update_lock);
}

int bind_evtchn_to_irqhandler(unsigned int evtchn,
			      irq_handler_t handler,
			      unsigned long irqflags,
			      const char *devname, void *dev_id)
{
	int irq, retval;

	irq = bind_evtchn_to_irq(evtchn);
	if (irq < 0)
		return irq;
	retval = request_irq(irq, handler, irqflags, devname, dev_id);
	if (retval != 0) {
		unbind_from_irq(irq);
		return retval;
	}

	return irq;
}
EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler);

int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
					  unsigned int remote_port,
					  irq_handler_t handler,
					  unsigned long irqflags,
					  const char *devname,
					  void *dev_id)
{
	int irq, retval;

	irq = bind_interdomain_evtchn_to_irq(remote_domain, remote_port);
	if (irq < 0)
		return irq;

	retval = request_irq(irq, handler, irqflags, devname, dev_id);
	if (retval != 0) {
		unbind_from_irq(irq);
		return retval;
	}

	return irq;
}
EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler);

int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
			    irq_handler_t handler,
			    unsigned long irqflags, const char *devname, void *dev_id)
{
	int irq, retval;

	irq = bind_virq_to_irq(virq, cpu);
	if (irq < 0)
		return irq;
	retval = request_irq(irq, handler, irqflags, devname, dev_id);
	if (retval != 0) {
		unbind_from_irq(irq);
		return retval;
	}

	return irq;
}
EXPORT_SYMBOL_GPL(bind_virq_to_irqhandler);

int bind_ipi_to_irqhandler(enum ipi_vector ipi,
			   unsigned int cpu,
			   irq_handler_t handler,
			   unsigned long irqflags,
			   const char *devname,
			   void *dev_id)
{
	int irq, retval;

	irq = bind_ipi_to_irq(ipi, cpu);
	if (irq < 0)
		return irq;

	irqflags |= IRQF_NO_SUSPEND | IRQF_FORCE_RESUME | IRQF_EARLY_RESUME;
	retval = request_irq(irq, handler, irqflags, devname, dev_id);
	if (retval != 0) {
		unbind_from_irq(irq);
		return retval;
	}

	return irq;
}

void unbind_from_irqhandler(unsigned int irq, void *dev_id)
{
	free_irq(irq, dev_id);
	unbind_from_irq(irq);
}
EXPORT_SYMBOL_GPL(unbind_from_irqhandler);

int evtchn_make_refcounted(unsigned int evtchn)
{
	int irq = evtchn_to_irq[evtchn];
	struct irq_info *info;

	if (irq == -1)
		return -ENOENT;

	info = irq_get_handler_data(irq);

	if (!info)
		return -ENOENT;

	WARN_ON(info->refcnt != -1);

	info->refcnt = 1;

	return 0;
}
EXPORT_SYMBOL_GPL(evtchn_make_refcounted);

int evtchn_get(unsigned int evtchn)
{
	int irq;
	struct irq_info *info;
	int err = -ENOENT;

	if (evtchn >= NR_EVENT_CHANNELS)
		return -EINVAL;

	mutex_lock(&irq_mapping_update_lock);

	irq = evtchn_to_irq[evtchn];
	if (irq == -1)
		goto done;

	info = irq_get_handler_data(irq);

	if (!info)
		goto done;

	err = -EINVAL;
	if (info->refcnt <= 0)
		goto done;

	info->refcnt++;
	err = 0;
 done:
	mutex_unlock(&irq_mapping_update_lock);

	return err;
}
EXPORT_SYMBOL_GPL(evtchn_get);

void evtchn_put(unsigned int evtchn)
{
	int irq = evtchn_to_irq[evtchn];
	if (WARN_ON(irq == -1))
		return;
	unbind_from_irq(irq);
}
EXPORT_SYMBOL_GPL(evtchn_put);

void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
{
	int irq = per_cpu(ipi_to_irq, cpu)[vector];
	BUG_ON(irq < 0);
	notify_remote_via_irq(irq);
}

irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
{
	struct shared_info *sh = HYPERVISOR_shared_info;
	int cpu = smp_processor_id();
	unsigned long *cpu_evtchn = per_cpu(cpu_evtchn_mask, cpu);
	int i;
	unsigned long flags;
	static DEFINE_SPINLOCK(debug_lock);
	struct vcpu_info *v;

	spin_lock_irqsave(&debug_lock, flags);

	printk("\nvcpu %d\n  ", cpu);

	for_each_online_cpu(i) {
		int pending;
		v = per_cpu(xen_vcpu, i);
		pending = (get_irq_regs() && i == cpu)
			? xen_irqs_disabled(get_irq_regs())
			: v->evtchn_upcall_mask;
		printk("%d: masked=%d pending=%d event_sel %0*lx\n  ", i,
		       pending, v->evtchn_upcall_pending,
		       (int)(sizeof(v->evtchn_pending_sel)*2),
		       v->evtchn_pending_sel);
	}
	v = per_cpu(xen_vcpu, cpu);

	printk("\npending:\n   ");
	for (i = ARRAY_SIZE(sh->evtchn_pending)-1; i >= 0; i--)
		printk("%0*lx%s", (int)sizeof(sh->evtchn_pending[0])*2,
		       sh->evtchn_pending[i],
		       i % 8 == 0 ? "\n   " : " ");
	printk("\nglobal mask:\n   ");
	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
		printk("%0*lx%s",
		       (int)(sizeof(sh->evtchn_mask[0])*2),
		       sh->evtchn_mask[i],
		       i % 8 == 0 ? "\n   " : " ");

	printk("\nglobally unmasked:\n   ");
	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
		printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2),
		       sh->evtchn_pending[i] & ~sh->evtchn_mask[i],
		       i % 8 == 0 ? "\n   " : " ");

	printk("\nlocal cpu%d mask:\n   ", cpu);
	for (i = (NR_EVENT_CHANNELS/BITS_PER_LONG)-1; i >= 0; i--)
		printk("%0*lx%s", (int)(sizeof(cpu_evtchn[0])*2),
		       cpu_evtchn[i],
		       i % 8 == 0 ? "\n   " : " ");

	printk("\nlocally unmasked:\n   ");
	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--) {
		unsigned long pending = sh->evtchn_pending[i]
			& ~sh->evtchn_mask[i]
			& cpu_evtchn[i];
		printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2),
		       pending, i % 8 == 0 ? "\n   " : " ");
	}

	printk("\npending list:\n");
	for (i = 0; i < NR_EVENT_CHANNELS; i++) {
		if (sync_test_bit(i, sh->evtchn_pending)) {
			int word_idx = i / BITS_PER_LONG;
			printk("  %d: event %d -> irq %d%s%s%s\n",
			       cpu_from_evtchn(i), i,
			       evtchn_to_irq[i],
			       sync_test_bit(word_idx, &v->evtchn_pending_sel)
					     ? "" : " l2-clear",
			       !sync_test_bit(i, sh->evtchn_mask)
					     ? "" : " globally-masked",
			       sync_test_bit(i, cpu_evtchn)
					     ? "" : " locally-masked");
		}
	}

	spin_unlock_irqrestore(&debug_lock, flags);

	return IRQ_HANDLED;
}

static DEFINE_PER_CPU(unsigned, xed_nesting_count);
static DEFINE_PER_CPU(unsigned int, current_word_idx);
static DEFINE_PER_CPU(unsigned int, current_bit_idx);

/*
 * Mask out the i least significant bits of w
 */
#define MASK_LSBS(w, i) (w & ((~0UL) << i))

/*
 * Search the CPUs pending events bitmasks.  For each one found, map
 * the event number to an irq, and feed it into do_IRQ() for
 * handling.
 *
 * Xen uses a two-level bitmap to speed searching.  The first level is
 * a bitset of words which contain pending event bits.  The second
 * level is a bitset of pending events themselves.
 */
static void __xen_evtchn_do_upcall(void)
{
	int start_word_idx, start_bit_idx;
	int word_idx, bit_idx;
	int i;
	int cpu = get_cpu();
	struct shared_info *s = HYPERVISOR_shared_info;
	struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu);
	unsigned count;

	do {
		unsigned long pending_words;

		vcpu_info->evtchn_upcall_pending = 0;

		if (__this_cpu_inc_return(xed_nesting_count) - 1)
			goto out;

#ifndef CONFIG_X86 /* No need for a barrier -- XCHG is a barrier on x86. */
		/* Clear master flag /before/ clearing selector flag. */
		wmb();
#endif
		pending_words = xchg(&vcpu_info->evtchn_pending_sel, 0);

		start_word_idx = __this_cpu_read(current_word_idx);
		start_bit_idx = __this_cpu_read(current_bit_idx);

		word_idx = start_word_idx;

		for (i = 0; pending_words != 0; i++) {
			unsigned long pending_bits;
			unsigned long words;

			words = MASK_LSBS(pending_words, word_idx);

			/*
			 * If we masked out all events, wrap to beginning.
			 */
			if (words == 0) {
				word_idx = 0;
				bit_idx = 0;
				continue;
			}
			word_idx = __ffs(words);

			pending_bits = active_evtchns(cpu, s, word_idx);
			bit_idx = 0; /* usually scan entire word from start */
			if (word_idx == start_word_idx) {
				/* We scan the starting word in two parts */
				if (i == 0)
					/* 1st time: start in the middle */
					bit_idx = start_bit_idx;
				else
					/* 2nd time: mask bits done already */
					bit_idx &= (1UL << start_bit_idx) - 1;
			}

			do {
				unsigned long bits;
				int port, irq;
				struct irq_desc *desc;

				bits = MASK_LSBS(pending_bits, bit_idx);

				/* If we masked out all events, move on. */
				if (bits == 0)
					break;

				bit_idx = __ffs(bits);

				/* Process port. */
				port = (word_idx * BITS_PER_LONG) + bit_idx;
				irq = evtchn_to_irq[port];

				if (irq != -1) {
					desc = irq_to_desc(irq);
					if (desc)
						generic_handle_irq_desc(irq, desc);
				}

				bit_idx = (bit_idx + 1) % BITS_PER_LONG;

				/* Next caller starts at last processed + 1 */
				__this_cpu_write(current_word_idx,
						 bit_idx ? word_idx :
						 (word_idx+1) % BITS_PER_LONG);
				__this_cpu_write(current_bit_idx, bit_idx);
			} while (bit_idx != 0);

			/* Scan start_l1i twice; all others once. */
			if ((word_idx != start_word_idx) || (i != 0))
				pending_words &= ~(1UL << word_idx);

			word_idx = (word_idx + 1) % BITS_PER_LONG;
		}

		BUG_ON(!irqs_disabled());

		count = __this_cpu_read(xed_nesting_count);
		__this_cpu_write(xed_nesting_count, 0);
	} while (count != 1 || vcpu_info->evtchn_upcall_pending);

out:

	put_cpu();
}

void xen_evtchn_do_upcall(struct pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs(regs);

	exit_idle();
	irq_enter();

	__xen_evtchn_do_upcall();

	irq_exit();
	set_irq_regs(old_regs);
}

void xen_hvm_evtchn_do_upcall(void)
{
	__xen_evtchn_do_upcall();
}
EXPORT_SYMBOL_GPL(xen_hvm_evtchn_do_upcall);

/* Rebind a new event channel to an existing irq. */
void rebind_evtchn_irq(int evtchn, int irq)
{
	struct irq_info *info = info_for_irq(irq);

	/* Make sure the irq is masked, since the new event channel
	   will also be masked. */
	disable_irq(irq);

	mutex_lock(&irq_mapping_update_lock);

	/* After resume the irq<->evtchn mappings are all cleared out */
	BUG_ON(evtchn_to_irq[evtchn] != -1);
	/* Expect irq to have been bound before,
	   so there should be a proper type */
	BUG_ON(info->type == IRQT_UNBOUND);

	xen_irq_info_evtchn_init(irq, evtchn);

	mutex_unlock(&irq_mapping_update_lock);

	/* new event channels are always bound to cpu 0 */
	irq_set_affinity(irq, cpumask_of(0));

	/* Unmask the event channel. */
	enable_irq(irq);
}

/* Rebind an evtchn so that it gets delivered to a specific cpu */
static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
{
	struct evtchn_bind_vcpu bind_vcpu;
	int evtchn = evtchn_from_irq(irq);

	if (!VALID_EVTCHN(evtchn))
		return -1;

	/*
	 * Events delivered via platform PCI interrupts are always
	 * routed to vcpu 0 and hence cannot be rebound.
	 */
	if (xen_hvm_domain() && !xen_have_vector_callback)
		return -1;

	/* Send future instances of this interrupt to other vcpu. */
	bind_vcpu.port = evtchn;
	bind_vcpu.vcpu = tcpu;

	/*
	 * If this fails, it usually just indicates that we're dealing with a
	 * virq or IPI channel, which don't actually need to be rebound. Ignore
	 * it, but don't do the xenlinux-level rebind in that case.
	 */
	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
		bind_evtchn_to_cpu(evtchn, tcpu);

	return 0;
}

static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
			    bool force)
{
	unsigned tcpu = cpumask_first(dest);

	return rebind_irq_to_cpu(data->irq, tcpu);
}

int resend_irq_on_evtchn(unsigned int irq)
{
	int masked, evtchn = evtchn_from_irq(irq);
	struct shared_info *s = HYPERVISOR_shared_info;

	if (!VALID_EVTCHN(evtchn))
		return 1;

	masked = sync_test_and_set_bit(evtchn, s->evtchn_mask);
	sync_set_bit(evtchn, s->evtchn_pending);
	if (!masked)
		unmask_evtchn(evtchn);

	return 1;
}

static void enable_dynirq(struct irq_data *data)
{
	int evtchn = evtchn_from_irq(data->irq);

	if (VALID_EVTCHN(evtchn))
		unmask_evtchn(evtchn);
}

static void disable_dynirq(struct irq_data *data)
{
	int evtchn = evtchn_from_irq(data->irq);

	if (VALID_EVTCHN(evtchn))
		mask_evtchn(evtchn);
}

static void ack_dynirq(struct irq_data *data)
{
	int evtchn = evtchn_from_irq(data->irq);

	irq_move_irq(data);

	if (VALID_EVTCHN(evtchn))
		clear_evtchn(evtchn);
}

static void mask_ack_dynirq(struct irq_data *data)
{
	disable_dynirq(data);
	ack_dynirq(data);
}

static int retrigger_dynirq(struct irq_data *data)
{
	int evtchn = evtchn_from_irq(data->irq);
	struct shared_info *sh = HYPERVISOR_shared_info;
	int ret = 0;

	if (VALID_EVTCHN(evtchn)) {
		int masked;

		masked = sync_test_and_set_bit(evtchn, sh->evtchn_mask);
		sync_set_bit(evtchn, sh->evtchn_pending);
		if (!masked)
			unmask_evtchn(evtchn);
		ret = 1;
	}

	return ret;
}

static void restore_pirqs(void)
{
	int pirq, rc, irq, gsi;
	struct physdev_map_pirq map_irq;
	struct irq_info *info;

	list_for_each_entry(info, &xen_irq_list_head, list) {
		if (info->type != IRQT_PIRQ)
			continue;

		pirq = info->u.pirq.pirq;
		gsi = info->u.pirq.gsi;
		irq = info->irq;

		/* save/restore of PT devices doesn't work, so at this point the
		 * only devices present are GSI based emulated devices */
		if (!gsi)
			continue;

		map_irq.domid = DOMID_SELF;
		map_irq.type = MAP_PIRQ_TYPE_GSI;
		map_irq.index = gsi;
		map_irq.pirq = pirq;

		rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq);
		if (rc) {
			printk(KERN_WARNING "xen map irq failed gsi=%d irq=%d pirq=%d rc=%d\n",
					gsi, irq, pirq, rc);
			xen_free_irq(irq);
			continue;
		}

		printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq);

		__startup_pirq(irq);
	}
}

static void restore_cpu_virqs(unsigned int cpu)
{
	struct evtchn_bind_virq bind_virq;
	int virq, irq, evtchn;

	for (virq = 0; virq < NR_VIRQS; virq++) {
		if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1)
			continue;

		BUG_ON(virq_from_irq(irq) != virq);

		/* Get a new binding from Xen. */
		bind_virq.virq = virq;
		bind_virq.vcpu = cpu;
		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
						&bind_virq) != 0)
			BUG();
		evtchn = bind_virq.port;

		/* Record the new mapping. */
		xen_irq_info_virq_init(cpu, irq, evtchn, virq);
		bind_evtchn_to_cpu(evtchn, cpu);
	}
}

static void restore_cpu_ipis(unsigned int cpu)
{
	struct evtchn_bind_ipi bind_ipi;
	int ipi, irq, evtchn;

	for (ipi = 0; ipi < XEN_NR_IPIS; ipi++) {
		if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1)
			continue;

		BUG_ON(ipi_from_irq(irq) != ipi);

		/* Get a new binding from Xen. */
		bind_ipi.vcpu = cpu;
		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
						&bind_ipi) != 0)
			BUG();
		evtchn = bind_ipi.port;

		/* Record the new mapping. */
		xen_irq_info_ipi_init(cpu, irq, evtchn, ipi);
		bind_evtchn_to_cpu(evtchn, cpu);
	}
}

/* Clear an irq's pending state, in preparation for polling on it */
void xen_clear_irq_pending(int irq)
{
	int evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn))
		clear_evtchn(evtchn);
}
EXPORT_SYMBOL(xen_clear_irq_pending);
void xen_set_irq_pending(int irq)
{
	int evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn))
		set_evtchn(evtchn);
}

bool xen_test_irq_pending(int irq)
{
	int evtchn = evtchn_from_irq(irq);
	bool ret = false;

	if (VALID_EVTCHN(evtchn))
		ret = test_evtchn(evtchn);

	return ret;
}

/* Poll waiting for an irq to become pending with timeout.  In the usual case,
 * the irq will be disabled so it won't deliver an interrupt. */
void xen_poll_irq_timeout(int irq, u64 timeout)
{
	evtchn_port_t evtchn = evtchn_from_irq(irq);

	if (VALID_EVTCHN(evtchn)) {
		struct sched_poll poll;

		poll.nr_ports = 1;
		poll.timeout = timeout;
		set_xen_guest_handle(poll.ports, &evtchn);

		if (HYPERVISOR_sched_op(SCHEDOP_poll, &poll) != 0)
			BUG();
	}
}
EXPORT_SYMBOL(xen_poll_irq_timeout);
/* Poll waiting for an irq to become pending.  In the usual case, the
 * irq will be disabled so it won't deliver an interrupt. */
void xen_poll_irq(int irq)
{
	xen_poll_irq_timeout(irq, 0 /* no timeout */);
}

/* Check whether the IRQ line is shared with other guests. */
int xen_test_irq_shared(int irq)
{
	struct irq_info *info = info_for_irq(irq);
	struct physdev_irq_status_query irq_status = { .irq = info->u.pirq.pirq };

	if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status))
		return 0;
	return !(irq_status.flags & XENIRQSTAT_shared);
}
EXPORT_SYMBOL_GPL(xen_test_irq_shared);

void xen_irq_resume(void)
{
	unsigned int cpu, evtchn;
	struct irq_info *info;

	init_evtchn_cpu_bindings();

	/* New event-channel space is not 'live' yet. */
	for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
		mask_evtchn(evtchn);

	/* No IRQ <-> event-channel mappings. */
	list_for_each_entry(info, &xen_irq_list_head, list)
		info->evtchn = 0; /* zap event-channel binding */

	for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
		evtchn_to_irq[evtchn] = -1;

	for_each_possible_cpu(cpu) {
		restore_cpu_virqs(cpu);
		restore_cpu_ipis(cpu);
	}

	restore_pirqs();
}

static struct irq_chip xen_dynamic_chip __read_mostly = {
	.name			= "xen-dyn",

	.irq_disable		= disable_dynirq,
	.irq_mask		= disable_dynirq,
	.irq_unmask		= enable_dynirq,

	.irq_ack		= ack_dynirq,
	.irq_mask_ack		= mask_ack_dynirq,

	.irq_set_affinity	= set_affinity_irq,
	.irq_retrigger		= retrigger_dynirq,
};

static struct irq_chip xen_pirq_chip __read_mostly = {
	.name			= "xen-pirq",

	.irq_startup		= startup_pirq,
	.irq_shutdown		= shutdown_pirq,
	.irq_enable		= enable_pirq,
	.irq_disable		= disable_pirq,

	.irq_mask		= disable_dynirq,
	.irq_unmask		= enable_dynirq,

	.irq_ack		= eoi_pirq,
	.irq_eoi		= eoi_pirq,
	.irq_mask_ack		= mask_ack_pirq,

	.irq_set_affinity	= set_affinity_irq,

	.irq_retrigger		= retrigger_dynirq,
};

static struct irq_chip xen_percpu_chip __read_mostly = {
	.name			= "xen-percpu",

	.irq_disable		= disable_dynirq,
	.irq_mask		= disable_dynirq,
	.irq_unmask		= enable_dynirq,

	.irq_ack		= ack_dynirq,
};

int xen_set_callback_via(uint64_t via)
{
	struct xen_hvm_param a;
	a.domid = DOMID_SELF;
	a.index = HVM_PARAM_CALLBACK_IRQ;
	a.value = via;
	return HYPERVISOR_hvm_op(HVMOP_set_param, &a);
}
EXPORT_SYMBOL_GPL(xen_set_callback_via);

#ifdef CONFIG_XEN_PVHVM
/* Vector callbacks are better than PCI interrupts to receive event
 * channel notifications because we can receive vector callbacks on any
 * vcpu and we don't need PCI support or APIC interactions. */
void xen_callback_vector(void)
{
	int rc;
	uint64_t callback_via;
	if (xen_have_vector_callback) {
		callback_via = HVM_CALLBACK_VECTOR(XEN_HVM_EVTCHN_CALLBACK);
		rc = xen_set_callback_via(callback_via);
		if (rc) {
			printk(KERN_ERR "Request for Xen HVM callback vector"
					" failed.\n");
			xen_have_vector_callback = 0;
			return;
		}
		printk(KERN_INFO "Xen HVM callback vector for event delivery is "
				"enabled\n");
		/* in the restore case the vector has already been allocated */
		if (!test_bit(XEN_HVM_EVTCHN_CALLBACK, used_vectors))
			alloc_intr_gate(XEN_HVM_EVTCHN_CALLBACK, xen_hvm_callback_vector);
	}
}
#else
void xen_callback_vector(void) {}
#endif

void __init xen_init_IRQ(void)
{
	int i, rc;

	evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
				    GFP_KERNEL);
	BUG_ON(!evtchn_to_irq);
	for (i = 0; i < NR_EVENT_CHANNELS; i++)
		evtchn_to_irq[i] = -1;

	init_evtchn_cpu_bindings();

	/* No event channels are 'live' right now. */
	for (i = 0; i < NR_EVENT_CHANNELS; i++)
		mask_evtchn(i);

	pirq_needs_eoi = pirq_needs_eoi_flag;

	if (xen_hvm_domain()) {
		xen_callback_vector();
		native_init_IRQ();
		/* pci_xen_hvm_init must be called after native_init_IRQ so that
		 * __acpi_register_gsi can point at the right function */
		pci_xen_hvm_init();
	} else {
		struct physdev_pirq_eoi_gmfn eoi_gmfn;

		irq_ctx_init(smp_processor_id());
		if (xen_initial_domain())
			pci_xen_initial_domain();

		pirq_eoi_map = (void *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
		eoi_gmfn.gmfn = virt_to_mfn(pirq_eoi_map);
		rc = HYPERVISOR_physdev_op(PHYSDEVOP_pirq_eoi_gmfn_v2, &eoi_gmfn);
		if (rc != 0) {
			free_page((unsigned long) pirq_eoi_map);
			pirq_eoi_map = NULL;
		} else
			pirq_needs_eoi = pirq_check_eoi_map;
	}
}